Merge tag 'arm-vfp-refactor-for-rmk' of git://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux into devel-stable

Refactor VFP support code and reimplement in C

The VFP related changes to permit kernel mode NEON in softirq context
resulted in some issues regarding en/disabling of sofirqs from asm code,
and this made it clear that it would be better to handle more of it from
C code.

Given that we already have infrastructure that associates undefined
instruction exceptions with handler code based on value/mask pairs, we
can easily move the dispatch of VFP and NEON instructions to C code once
we reimplement the actual VFP support routine (which reasons about how
to deal with the exception and whether any emulation is needed) in C
code first.

With those out of the way, we can drop the partial decoding logic in asm
that reasons about which ISA is being used by user space, as the
remaining cases are all 32-bit ARM only. This leaves a FPE specific
routine with some iWMMXT logic that is easily duplicated in C as well,
allowing us to move the FPE asm code into the FPE asm source file, and
out of the shared entry code.

8 files changed, 50 insertions, 251 deletions

diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 38121c59cbc2..f9c7111c1d65 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -47,7 +47,6 @@ int main(void)
   DEFINE(TI_CPU_DOMAIN,		offsetof(struct thread_info, cpu_domain));
   DEFINE(TI_CPU_SAVE,		offsetof(struct thread_info, cpu_context));
   DEFINE(TI_ABI_SYSCALL,	offsetof(struct thread_info, abi_syscall));
-  DEFINE(TI_USED_CP,		offsetof(struct thread_info, used_cp));
   DEFINE(TI_TP_VALUE,		offsetof(struct thread_info, tp_value));
   DEFINE(TI_FPSTATE,		offsetof(struct thread_info, fpstate));
 #ifdef CONFIG_VFP
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index c39303e5c234..682e92664b07 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -446,258 +446,26 @@ ENDPROC(__irq_usr)
 __und_usr:
 	usr_entry uaccess=0
 
-	mov	r2, r4
-	mov	r3, r5
-
-	@ r2 = regs->ARM_pc, which is either 2 or 4 bytes ahead of the
-	@      faulting instruction depending on Thumb mode.
-	@ r3 = regs->ARM_cpsr
-	@
-	@ The emulation code returns using r9 if it has emulated the
-	@ instruction, or the more conventional lr if we are to treat
-	@ this as a real undefined instruction
-	@
-	badr	r9, ret_from_exception
-
 	@ IRQs must be enabled before attempting to read the instruction from
 	@ user space since that could cause a page/translation fault if the
 	@ page table was modified by another CPU.
 	enable_irq
 
-	tst	r3, #PSR_T_BIT			@ Thumb mode?
-	bne	__und_usr_thumb
-	sub	r4, r2, #4			@ ARM instr at LR - 4
-1:	ldrt	r0, [r4]
- ARM_BE8(rev	r0, r0)				@ little endian instruction
-
-	uaccess_disable ip
-
-	@ r0 = 32-bit ARM instruction which caused the exception
-	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
-	@ r4 = PC value for the faulting instruction
-	@ lr = 32-bit undefined instruction function
-	badr	lr, __und_usr_fault_32
-	b	call_fpe
-
-__und_usr_thumb:
-	@ Thumb instruction
-	sub	r4, r2, #2			@ First half of thumb instr at LR - 2
-#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7
-/*
- * Thumb-2 instruction handling.  Note that because pre-v6 and >= v6 platforms
- * can never be supported in a single kernel, this code is not applicable at
- * all when __LINUX_ARM_ARCH__ < 6.  This allows simplifying assumptions to be
- * made about .arch directives.
- */
-#if __LINUX_ARM_ARCH__ < 7
-/* If the target CPU may not be Thumb-2-capable, a run-time check is needed: */
-	ldr_va	r5, cpu_architecture
-	cmp	r5, #CPU_ARCH_ARMv7
-	blo	__und_usr_fault_16		@ 16bit undefined instruction
-/*
- * The following code won't get run unless the running CPU really is v7, so
- * coding round the lack of ldrht on older arches is pointless.  Temporarily
- * override the assembler target arch with the minimum required instead:
- */
-	.arch	armv6t2
+	tst	r5, #PSR_T_BIT			@ Thumb mode?
+	mov	r1, #2				@ set insn size to 2 for Thumb
+	bne	0f				@ handle as Thumb undef exception
+#ifdef CONFIG_FPE_NWFPE
+	adr	r9, ret_from_exception
+	bl	call_fpe			@ returns via R9 on success
 #endif
-2:	ldrht	r5, [r4]
-ARM_BE8(rev16	r5, r5)				@ little endian instruction
-	cmp	r5, #0xe800			@ 32bit instruction if xx != 0
-	blo	__und_usr_fault_16_pan		@ 16bit undefined instruction
-3:	ldrht	r0, [r2]
-ARM_BE8(rev16	r0, r0)				@ little endian instruction
+	mov	r1, #4				@ set insn size to 4 for ARM
+0:	mov	r0, sp
 	uaccess_disable ip
-	add	r2, r2, #2			@ r2 is PC + 2, make it PC + 4
-	str	r2, [sp, #S_PC]			@ it's a 2x16bit instr, update
-	orr	r0, r0, r5, lsl #16
-	badr	lr, __und_usr_fault_32
-	@ r0 = the two 16-bit Thumb instructions which caused the exception
-	@ r2 = PC value for the following Thumb instruction (:= regs->ARM_pc)
-	@ r4 = PC value for the first 16-bit Thumb instruction
-	@ lr = 32bit undefined instruction function
-
-#if __LINUX_ARM_ARCH__ < 7
-/* If the target arch was overridden, change it back: */
-#ifdef CONFIG_CPU_32v6K
-	.arch	armv6k
-#else
-	.arch	armv6
-#endif
-#endif /* __LINUX_ARM_ARCH__ < 7 */
-#else /* !(CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7) */
-	b	__und_usr_fault_16
-#endif
+	bl	__und_fault
+	b	ret_from_exception
  UNWIND(.fnend)
 ENDPROC(__und_usr)
 
-/*
- * The out of line fixup for the ldrt instructions above.
- */
-	.pushsection .text.fixup, "ax"
-	.align	2
-4:	str     r4, [sp, #S_PC]			@ retry current instruction
-	ret	r9
-	.popsection
-	.pushsection __ex_table,"a"
-	.long	1b, 4b
-#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7
-	.long	2b, 4b
-	.long	3b, 4b
-#endif
-	.popsection
-
-/*
- * Check whether the instruction is a co-processor instruction.
- * If yes, we need to call the relevant co-processor handler.
- *
- * Note that we don't do a full check here for the co-processor
- * instructions; all instructions with bit 27 set are well
- * defined.  The only instructions that should fault are the
- * co-processor instructions.  However, we have to watch out
- * for the ARM6/ARM7 SWI bug.
- *
- * NEON is a special case that has to be handled here. Not all
- * NEON instructions are co-processor instructions, so we have
- * to make a special case of checking for them. Plus, there's
- * five groups of them, so we have a table of mask/opcode pairs
- * to check against, and if any match then we branch off into the
- * NEON handler code.
- *
- * Emulators may wish to make use of the following registers:
- *  r0  = instruction opcode (32-bit ARM or two 16-bit Thumb)
- *  r2  = PC value to resume execution after successful emulation
- *  r9  = normal "successful" return address
- *  r10 = this threads thread_info structure
- *  lr  = unrecognised instruction return address
- * IRQs enabled, FIQs enabled.
- */
-	@
-	@ Fall-through from Thumb-2 __und_usr
-	@
-#ifdef CONFIG_NEON
-	get_thread_info r10			@ get current thread
-	adr	r6, .LCneon_thumb_opcodes
-	b	2f
-#endif
-call_fpe:
-	get_thread_info r10			@ get current thread
-#ifdef CONFIG_NEON
-	adr	r6, .LCneon_arm_opcodes
-2:	ldr	r5, [r6], #4			@ mask value
-	ldr	r7, [r6], #4			@ opcode bits matching in mask
-	cmp	r5, #0				@ end mask?
-	beq	1f
-	and	r8, r0, r5
-	cmp	r8, r7				@ NEON instruction?
-	bne	2b
-	mov	r7, #1
-	strb	r7, [r10, #TI_USED_CP + 10]	@ mark CP#10 as used
-	strb	r7, [r10, #TI_USED_CP + 11]	@ mark CP#11 as used
-	b	do_vfp				@ let VFP handler handle this
-1:
-#endif
-	tst	r0, #0x08000000			@ only CDP/CPRT/LDC/STC have bit 27
-	tstne	r0, #0x04000000			@ bit 26 set on both ARM and Thumb-2
-	reteq	lr
-	and	r8, r0, #0x00000f00		@ mask out CP number
-	mov	r7, #1
-	add	r6, r10, r8, lsr #8		@ add used_cp[] array offset first
-	strb	r7, [r6, #TI_USED_CP]		@ set appropriate used_cp[]
-#ifdef CONFIG_IWMMXT
-	@ Test if we need to give access to iWMMXt coprocessors
-	ldr	r5, [r10, #TI_FLAGS]
-	rsbs	r7, r8, #(1 << 8)		@ CP 0 or 1 only
-	movscs	r7, r5, lsr #(TIF_USING_IWMMXT + 1)
-	bcs	iwmmxt_task_enable
-#endif
- ARM(	add	pc, pc, r8, lsr #6	)
- THUMB(	lsr	r8, r8, #6		)
- THUMB(	add	pc, r8			)
-	nop
-
-	ret.w	lr				@ CP#0
-	W(b)	do_fpe				@ CP#1 (FPE)
-	W(b)	do_fpe				@ CP#2 (FPE)
-	ret.w	lr				@ CP#3
-	ret.w	lr				@ CP#4
-	ret.w	lr				@ CP#5
-	ret.w	lr				@ CP#6
-	ret.w	lr				@ CP#7
-	ret.w	lr				@ CP#8
-	ret.w	lr				@ CP#9
-#ifdef CONFIG_VFP
-	W(b)	do_vfp				@ CP#10 (VFP)
-	W(b)	do_vfp				@ CP#11 (VFP)
-#else
-	ret.w	lr				@ CP#10 (VFP)
-	ret.w	lr				@ CP#11 (VFP)
-#endif
-	ret.w	lr				@ CP#12
-	ret.w	lr				@ CP#13
-	ret.w	lr				@ CP#14 (Debug)
-	ret.w	lr				@ CP#15 (Control)
-
-#ifdef CONFIG_NEON
-	.align	6
-
-.LCneon_arm_opcodes:
-	.word	0xfe000000			@ mask
-	.word	0xf2000000			@ opcode
-
-	.word	0xff100000			@ mask
-	.word	0xf4000000			@ opcode
-
-	.word	0x00000000			@ mask
-	.word	0x00000000			@ opcode
-
-.LCneon_thumb_opcodes:
-	.word	0xef000000			@ mask
-	.word	0xef000000			@ opcode
-
-	.word	0xff100000			@ mask
-	.word	0xf9000000			@ opcode
-
-	.word	0x00000000			@ mask
-	.word	0x00000000			@ opcode
-#endif
-
-do_fpe:
-	add	r10, r10, #TI_FPSTATE		@ r10 = workspace
-	ldr_va	pc, fp_enter, tmp=r4		@ Call FP module USR entry point
-
-/*
- * The FP module is called with these registers set:
- *  r0  = instruction
- *  r2  = PC+4
- *  r9  = normal "successful" return address
- *  r10 = FP workspace
- *  lr  = unrecognised FP instruction return address
- */
-
-	.pushsection .data
-	.align	2
-ENTRY(fp_enter)
-	.word	no_fp
-	.popsection
-
-ENTRY(no_fp)
-	ret	lr
-ENDPROC(no_fp)
-
-__und_usr_fault_32:
-	mov	r1, #4
-	b	1f
-__und_usr_fault_16_pan:
-	uaccess_disable ip
-__und_usr_fault_16:
-	mov	r1, #2
-1:	mov	r0, sp
-	badr	lr, ret_from_exception
-	b	__und_fault
-ENDPROC(__und_usr_fault_32)
-ENDPROC(__und_usr_fault_16)
-
 	.align	5
 __pabt_usr:
 	usr_entry
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index d2b4ac06e4ed..a0218c4867b9 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -58,9 +58,19 @@
 	.text
 	.arm
 
+ENTRY(iwmmxt_undef_handler)
+	push		{r9, r10, lr}
+	get_thread_info	r10
+	mov		r9, pc
+	b		iwmmxt_task_enable
+	mov		r0, #0
+	pop		{r9, r10, pc}
+ENDPROC(iwmmxt_undef_handler)
+
 /*
  * Lazy switching of Concan coprocessor context
  *
+ * r0  = struct pt_regs pointer
  * r10 = struct thread_info pointer
  * r9  = ret_from_exception
  * lr  = undefined instr exit
@@ -84,12 +94,12 @@ ENTRY(iwmmxt_task_enable)
 	PJ4(mcr	p15, 0, r2, c1, c0, 2)
 
 	ldr	r3, =concan_owner
-	add	r0, r10, #TI_IWMMXT_STATE	@ get task Concan save area
-	ldr	r2, [sp, #60]			@ current task pc value
+	ldr	r2, [r0, #S_PC]			@ current task pc value
 	ldr	r1, [r3]			@ get current Concan owner
-	str	r0, [r3]			@ this task now owns Concan regs
 	sub	r2, r2, #4			@ adjust pc back
-	str	r2, [sp, #60]
+	str	r2, [r0, #S_PC]
+	add	r0, r10, #TI_IWMMXT_STATE	@ get task Concan save area
+	str	r0, [r3]			@ this task now owns Concan regs
 
 	mrc	p15, 0, r2, c2, c0, 0
 	mov	r2, r2				@ cpwait
diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c
index 1d1fb22f44f3..4bca8098c4ff 100644
--- a/arch/arm/kernel/pj4-cp0.c
+++ b/arch/arm/kernel/pj4-cp0.c
@@ -126,6 +126,7 @@ static int __init pj4_cp0_init(void)
 	pr_info("PJ4 iWMMXt v%d coprocessor enabled.\n", vers);
 	elf_hwcap |= HWCAP_IWMMXT;
 	thread_register_notifier(&iwmmxt_notifier_block);
+	register_iwmmxt_undef_handler();
 #endif
 
 	return 0;
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 0e8ff85890ad..e16ed102960c 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -222,7 +222,6 @@ void flush_thread(void)
 
 	flush_ptrace_hw_breakpoint(tsk);
 
-	memset(thread->used_cp, 0, sizeof(thread->used_cp));
 	memset(&tsk->thread.debug, 0, sizeof(struct debug_info));
 	memset(&thread->fpstate, 0, sizeof(union fp_state));
 
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 2d8e2516906b..2b945b9bd366 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -584,8 +584,6 @@ static int fpa_set(struct task_struct *target,
 {
 	struct thread_info *thread = task_thread_info(target);
 
-	thread->used_cp[1] = thread->used_cp[2] = 1;
-
 	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 		&thread->fpstate,
 		0, sizeof(struct user_fp));
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 53be7ea6181b..9d2192156087 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -308,6 +308,29 @@ static int unwind_exec_pop_subset_r0_to_r3(struct unwind_ctrl_block *ctrl,
 	return URC_OK;
 }
 
+static unsigned long unwind_decode_uleb128(struct unwind_ctrl_block *ctrl)
+{
+	unsigned long bytes = 0;
+	unsigned long insn;
+	unsigned long result = 0;
+
+	/*
+	 * unwind_get_byte() will advance `ctrl` one instruction at a time, so
+	 * loop until we get an instruction byte where bit 7 is not set.
+	 *
+	 * Note: This decodes a maximum of 4 bytes to output 28 bits data where
+	 * max is 0xfffffff: that will cover a vsp increment of 1073742336, hence
+	 * it is sufficient for unwinding the stack.
+	 */
+	do {
+		insn = unwind_get_byte(ctrl);
+		result |= (insn & 0x7f) << (bytes * 7);
+		bytes++;
+	} while (!!(insn & 0x80) && (bytes != sizeof(result)));
+
+	return result;
+}
+
 /*
  * Execute the current unwind instruction.
  */
@@ -361,7 +384,7 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 		if (ret)
 			goto error;
 	} else if (insn == 0xb2) {
-		unsigned long uleb128 = unwind_get_byte(ctrl);
+		unsigned long uleb128 = unwind_decode_uleb128(ctrl);
 
 		ctrl->vrs[SP] += 0x204 + (uleb128 << 2);
 	} else {
diff --git a/arch/arm/kernel/xscale-cp0.c b/arch/arm/kernel/xscale-cp0.c
index ed4f6e77616d..00d00d3aae97 100644
--- a/arch/arm/kernel/xscale-cp0.c
+++ b/arch/arm/kernel/xscale-cp0.c
@@ -166,6 +166,7 @@ static int __init xscale_cp0_init(void)
 		pr_info("XScale iWMMXt coprocessor detected.\n");
 		elf_hwcap |= HWCAP_IWMMXT;
 		thread_register_notifier(&iwmmxt_notifier_block);
+		register_iwmmxt_undef_handler();
 #endif
 	} else {
 		pr_info("XScale DSP coprocessor detected.\n");